Metraipolis › archive › dc_a277ce1c29ee

D-IMPL: A Diffusion-based Solver for Parameterized BBOs — arXiv:2609.22752

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22752
License (as archived)
CC0-1.0
Archived
2026-10-09T07:06:48.199Z
SHA-256 of the archived text
b99576413f7da88c629f3679f43db23c0385dd2d40edb4a6d69faf3e245b24de
Stable URL of this page
https://metraipolis.com/documento/dc_a277ce1c29ee

How to cite

D-IMPL: A Diffusion-based Solver for Parameterized BBOs — arXiv:2609.22752 — arXiv (en), https://arxiv.org/abs/2609.22752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a277ce1c29ee (Metraipolis archive dc_a277ce1c29ee, sha256 b99576413f7da88c629f3679f43db23c0385dd2d40edb4a6d69faf3e245b24de)
BibTeX
@misc{dca277ce1c29ee,
  title = {D-IMPL: A Diffusion-based Solver for Parameterized BBOs — arXiv:2609.22752},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22752},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a277ce1c29ee; sha256 b99576413f7da88c629f3679f43db23c0385dd2d40edb4a6d69faf3e245b24de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models have demonstrated strong power in generative modeling tasks across multiple domains, exhibiting a remarkable capability of learning complex distributions from samples. In this paper, we leverage such capability to design an efficient universal diffusion-based solver for parameterized black-box optimizations (BBO), where the optimizer has only black-box access to queries of the objective function at the learning stage, yet is able to reduce the additional computational cost at the inference stage for each BBO instance while also capturing the potential multi-modal landscape of non-convex objectives. To cast our formulation as a compatible generative modeling task, we introduce the notion of minimization policy as a new solution concept, which defines a sampling distribution over the solutions that should concentrate around the minimizer set for each BBO instance. We then propose Diffusion-based Iterative Minimization Policy Learning (D-IMPL), a practical generative-model-based solver for solving parameterized BBOs that employs diffusion models to learn a minimization policy, whose density is proportional to the exponential of the negated objective values, thereby amortizing the computational costs across different BBO instances. Furthermore, we demonstrate the performance of our D-IMPL algorithm by establishing a sample complexity guarantee showing that a $\delta$-approximate minimization policy can be effectively learned within $O(\log(1/\delta))$ iterations, and by extensive empirical evaluations over a range of constrained and unconstrained BBO tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.22752 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:58:09.215Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).